基于X射线的气缸套缺陷检测研究

Study on Automatic Defect Detection Technology of the Cylinder Liner Based on X-ray

对于气缸套产品常见缺陷的快速自动识别与检测,依旧是行业内没有很好解决的难题。方案研制了基于X射线的气缸套缺陷检测系统。首先,搭建了基于X射线机器视觉技术的气缸套自动检测硬件平台;其次,针对气缸套的快速目标检测,采用多帧叠加和直方图均衡化对气缸套图像进行快速滤波,对不存在疑似缺陷的图像直接生成检测结果并删除图像;最后,仅针对存在疑似缺陷的气缸套图像采用改进的最大相关法进行阈值分割,生成最终检测结果。实验结果表明检测准确率为91.1%,方案在保证检测准确率的情况下,实现了气缸套产品缺陷的自动、快速检测。

It is still an unresolved issue to test the cylinder liner in industry application. The program developes X-ray visual cylinder liner defect detection system. First of all, the cylinder liner automatic defect detection hardware platform based on X-ray is established. Secondly, aiming at fast target detection, quickly filtering is used to all cylinders liners single-wall circumferential sequence images after multi-frame overlay and histogram equalization and for images that do not have suspected detects, directly generating test results and delete images. Finally, using the improved maximum correlation method for threshold segmentation to extract the defect area of the cylinder liner, generate the final test results. Experiments prove that this program has faster detection and discrimination speed than traditional detection method and the detection accuracy is 91.1%.